research-article

icuARM-II: improving the reliability of personalized risk prediction in pediatric intensive care units

Authors:

Chih-Wen Cheng,

Nikhil Chanani,

May D. WangAuthors Info & Claims

BCB '14: Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics

Pages 211 - 219

https://doi.org/10.1145/2649387.2649440

Published: 20 September 2014 Publication History

Abstract

Clinicians in intensive care units (ICUs) rely on standardized scores as risk prediction models to predict a patient's vulnerability to life-threatening events. Current scales calculate scores from a fixed set of conditions collected within a specific time window. However, modern monitoring technologies generate complex, temporal, and multimodal patient data that conventional prediction scales cannot fully utilize. Thus, a more sophisticated model is needed to tailor individual characteristics and incorporate multiple temporal modalities for a personalized risk prediction. Furthermore, most scales focus on adult patients. To address this need, we propose a new ICU risk prediction system, called icuARM-II, using a large-scaled pediatric ICU database from Children's Healthcare of Atlanta. This novel database contains clinical data collected in 5,739 ICU visits from 4,975 patients. We propose a temporal association rule mining framework giving a potential to predict risks based on all available conditions without being restricted by a fixed observation window. We also develop a new metric that rigidly assesses the reliability of all generated association rules. In addition, icuARM-II features an interactive user interface. Using icuARM-II, our results showed a use case of short-term mortality prediction using lab testing results, which demonstrated a potential for reliable ICU risk prediction using personalized clinical data in a previously neglected population.

References

[1]

Miller, G. A. The magical number seven, plus or minus two: some limits on our capacity for processing information. Psychological review, 63, 2 (1956), 81.

[2]

Rosenberg, A. L. Recent innovations in intensive care unit risk-prediction models. Current opinion in critical care, 8, 4 (2002), 321--330.

[3]

Knaus, W. A., Draper, E. A., Wagner, D. P. and Zimmerman, J. E. APACHE II: a severity of disease classification system. Critical care medicine, 13, 10 (1985), 818--829.

[4]

Lemeshow, S., Teres, D., Klar, J., Avrunin, J. S., Gehlbach, S. H. and Rapoport, J. Mortality Probability Models (MPM II) based on an international cohort of intensive care unit patients. Jama, 270, 20 (1993), 2478--2486.

[5]

Le Gall, J.-R., Lemeshow, S. and Saulnier, F. A new simplified acute physiology score (SAPS II) based on a European/North American multicenter study. Jama, 270, 24 (1993), 2957--2963.

[6]

Marshall, J. C., Cook, D. J., Christou, N. V., Bernard, G. R., Sprung, C. L. and Sibbald, W. J. Multiple organ dysfunction score: a reliable descriptor of a complex clinical outcome. Critical care medicine, 23, 10 (1995), 1638--1652.

[7]

Vincent, J.-L., Ferreira, F. and Moreno, R. Scoring systems for assessing organ dysfunction and survival. Critical care clinics, 16, 2 (2000), 353--366.

[8]

Le Gall, J.-R., Klar, J., Lemeshow, S., Saulnier, F., Alberti, C., Artigas, A. and Teres, D. The Logistic Organ Dysfunction system: a new way to assess organ dysfunction in the intensive care unit. Jama, 276, 10 (1996), 802--810.

[9]

Fialho, A. S., Cismondi, F., Vieira, S. M., Reti, S. R., Sousa, J. M. and Finkelstein, S. N. Data mining using clinical physiology at discharge to predict ICU readmissions. Expert Systems with Applications, 39, 18 (2012), 13158--13165.

Digital Library

[10]

Clark, P. A. and Lettieri, C. J. Clinical model for predicting prolonged mechanical ventilation. Journal of critical care, 28, 5 (2013), 880. e881--880. e887.

[11]

Elstein, A. S. Heuristics and biases: selected errors in clinical reasoning. Academic Medicine, 74, 7 (1999), 791--794.

[12]

Zygun, D. A., Laupland, K. B., Fick, G. H., Sandham, J. D. and Doig, C. J. Neuroanesthesia and Intensive Care Limited ability of SOFA and MOD scores to discriminate outcome: a prospective evaluation in 1,436 patients. Canadian Journal of Anesthesia, 52, 3 (2005), 302--308.

[13]

Khwannimit, B. A comparison of three organ dysfunction scores: MODS, SOFA and LOD for predicting ICU mortality in critically ill patients. Medical Association of Thailand, Journal of 90, 6 (2007), 1074.

[14]

Holtfreter, B., Bandt, C., Kuhn, S. O., Grunwald, U., Lehmann, C., Schütt, C. and Gründling, M. Serum osmolality and outcome in intensive care unit patients. Acta anaesthesiologica scandinavica, 50, 8 (2006), 970--977.

[15]

Timsit, J.-F., Fosse, J.-P., Troché, G., de Lassence, A., Alberti, C., Garrouste-Orgeas, M., Bornstain, C., Adrie, C., Cheval, C. and Chevret, S. Calibration and discrimination by daily Logistic Organ Dysfunction scoring comparatively with daily Sequential Organ Failure Assessment scoring for predicting hospital mortality in critically ill patients*. Critical care medicine, 30, 9 (2002), 2003--2013.

[16]

Cheng, C.-W., Chanani, N., Venugopalan, J., Maher, K. and Wang, D. icuARM--An ICU Clinical Decision Support System Using Association Rule Mining. Translational Engineering in Health and Medicine (JTEHM), IEEE Journal of, 1(2013).

[17]

Yoo, I., Alafaireet, P., Marinov, M., Pena-Hernandez, K., Gopidi, R., Chang, J.-F. and Hua, L. Data mining in healthcare and biomedicine: a survey of the literature. Journal of medical systems, 36, 4 (2012), 2431--2448.

Digital Library

[18]

Agrawal, R., Imieliński, T. and Swami, A. Mining association rules between sets of items in large databases. In Proceedings of the ACM SIGMOD Record, 1993, 207--216, ACM.

Digital Library

[19]

Agrawal, R. and Srikant, R. Fast algorithms for mining association rules. In Proceedings of the Proc. 20th int. conf. very large data bases, VLDB, 1994, 487--499, ACM.

Digital Library

[20]

Creighton, C. and Hanash, S. Mining gene expression databases for association rules. Bioinformatics, 19, 1 (2003), 79--86.

[21]

Leung, K.-S., Wong, K.-C., Chan, T.-M., Wong, M.-H., Lee, K.-H., Lau, C.-K. and Tsui, S. K. Discovering protein--DNA binding sequence patterns using association rule mining. Nucleic acids research, 38, 19 (2010), 6324--6337.

[22]

Konias, S., Giaglis, G., Gogou, G., Bamidis, P. and Maglaveras, N. Uncertainty rule generation on a home care database of heart failure patients. In Proceedings of the Computers in Cardiology, 2003, 765--768, IEEE.

[23]

Ordonez, C., Omiecinski, E., de Braal, L., Santana, C. A., Ezquerra, N. F., Taboada, J. A., Cooke, C. D., Krawczynska, E. and Garcia, E. V. Mining Constrained Association Rules to Predict Heart Disease. In Proceedings of the nternational Conference on Data Mining (ICDM), 2001, 433--440.

Digital Library

[24]

Shan, Y., Jeacocke, D., Murray, D. W. and Sutinen, A. Mining medical specialist billing patterns for health service management. In Proceedings of the Proceedings of the 7th Australasian Data Mining Conference-Volume 87, 2008, 105--110, Australian Computer Society, Inc.

Digital Library

[25]

Bellazzi, R., Larizza, C., Magni, P. and Bellazzi, R. Temporal data mining for the quality assessment of hemodialysis services. Artificial Intelligence in Medicine, 34, 1 (2005), 25--39.

Digital Library

[26]

Chaves, R., Górriz, J., Ramírez, J., Illán, I., Salas-Gonzalez, D. and Gómez-Río, M. Efficient mining of association rules for the early diagnosis of Alzheimer's disease. Physics in medicine and biology, 56, 18 (2011), 6047.

[27]

Cheng, C.-W., Burns, T. G. and Wang, M. D. Mining Association Rules for Neurobehavioral and Motor Disorders in Children Diagnosed with Cerebral Palsy. In Proceedings of the IEEE International Conference on Healthcare Informatics (ICHI), 2013, 258--263, IEEE.

Digital Library

[28]

Cheng, C.-W., Martin, G. S., Wu, P.-Y. and Wang, M. D. PHARM-Association Rule Mining for Predictive Health. In Proceedings of the The International Conference on Health Informatics, 2014, 114--117, Springer.

[29]

Saeed, M., Villarroel, M., Reisner, A. T., Clifford, G., Lehman, L.-W., Moody, G., Heldt, T., Kyaw, T. H., Moody, B. and Mark, R. G. Multiparameter Intelligent Monitoring in Intensive Care II (MIMIC-II): a public-access intensive care unit database. Critical care medicine, 39, 5 (2011), 952.

[30]

Verma, K., Vyas, O. P. and Vyas, R. Temporal approach to association rule mining using t-tree and p-tree. Springer, City, 2005.

Digital Library

[31]

Ale, J. M. and Rossi, G. H. An approach to discovering temporal association rules. ACM, City, 2000.

Digital Library

[32]

Provost, F. J., Fawcett, T. and Kohavi, R. The case against accuracy estimation for comparing induction algorithms. In Proceedings of the ICML, 1998, 445--453.

Digital Library

[33]

Ma, B. L. W. H. Y. Integrating classification and association rule mining. In Proceedings of the Proceedings of the 4th, 1998.

[34]

Roberts, D. E., Bell, D. D., Ostryzniuk, T., Dobson, K., Oppenheimer, L., Martens, D., Honcharik, N., Cramp, H., Loewen, E. and Bodnar, S. Eliminating needless testing in intensive care-an information-based team management approach. Critical care medicine, 21, 10 (1993), 1452--1458.

[35]

Zimmerman, J. E., Kramer, A. A., McNair, D. S. and Malila, F. M. Acute Physiology and Chronic Health Evaluation (APACHE) IV: Hospital mortality assessment for today's critically ill patients*. Critical care medicine, 34, 5 (2006), 1297--1310.

[36]

Mehari, S. and Havill, J. Written guidelines for laboratory testing in intensive care-still effective after 3 years. Critical Care and Resuscitation, 3, 3 (2001), 158.

[37]

Garland, A., Shaman, Z., Baron, J. and Connors Jr, A. F. Physician-attributable differences in intensive care unit costs: a single-center study. American journal of respiratory and critical care medicine, 174, 11 (2006), 1206--1210.

[38]

Zhong, S. Semi-supervised sequence classification with hmms. International Journal of Pattern Recognition and Artificial Intelligence, 19, 02 (2005), 165--182.

[39]

Wei, L. and Keogh, E. Semi-supervised time series classification. In Proceedings of the Proceedings of the 12th ACM SIGKDD international conference on Knowledge discovery and data mining, 2006, 748--753, ACM.

Digital Library

[40]

Zadrozny, B. and Elkan, C. Transforming classifier scores into accurate multiclass probability estimates. ACM, City, 2002.

Digital Library

[41]

Jiang, X., Osl, M., Kim, J. and Ohno-Machado, L. Calibrating predictive model estimates to support personalized medicine. Journal of the American Medical Informatics Association, 19, 2 (2012), 263--274.

Cited By

Rubio Delgado ERodríguez-Mazahua LPalet Guzmán JCervantes JCervantes JPeláez-Camarena SLópez-Chau A(2018)Analysis of Medical Opinions about the Nonrealization of Autopsies in a Mexican Hospital Using Association Rules and Bayesian NetworksScientific Programming10.1155/2018/43040172018Online publication date: 13-Feb-2018
https://dl.acm.org/doi/10.1155/2018/4304017
Rubio Delgado ERodríguez-Mazahua LPeláez-Camarena SAntonio Palet Guzmán JLópez-Chau A(2017)Association Analysis of Medical Opinions About the Non-realization of Autopsies in a Mexican HospitalNew Perspectives on Applied Industrial Tools and Techniques10.1007/978-3-319-56871-3_12(233-251)Online publication date: 17-Jun-2017
https://doi.org/10.1007/978-3-319-56871-3_12
Cheng CWang M(2015)Improving personalized clinical risk prediction based on causality-based association rulesProceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics10.1145/2808719.2808759(386-392)Online publication date: 9-Sep-2015
https://dl.acm.org/doi/10.1145/2808719.2808759

Index Terms

icuARM-II: improving the reliability of personalized risk prediction in pediatric intensive care units
1. Applied computing
  1. Life and medical sciences

Recommendations

Improving personalized clinical risk prediction based on causality-based association rules
BCB '15: Proceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics

Developing clinical risk prediction models is one of the main tasks of healthcare data mining. Advanced data collection techniques in current Big Data era have created an emerging and urgent need for scalable, computer-based data mining methods. These ...
An informatics architecture for the Virtual Pediatric Intensive Care Unit
CBMS '11: Proceedings of the 2011 24th International Symposium on Computer-Based Medical Systems

The Laura P. and Leland K. Whittier Virtual Pediatric Intensive Care Unit (VPICU) is an ambitious research network focused on building online databases for improving decision-making in pediatric intensive care units. Increasingly, there is a need to ...
Plenary lecture II: health informatics in next generation health care
BEBI'08: Proceedings of the 1st WSEAS international conference on Biomedical electronics and biomedical informatics

Due to the problem of unequal in health care for the people who live far away from the city center and unutilized health personnel to distribute to the rural area, we need Health Informatics to solve this problems. The Health Informatics here is cover ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

BCB '14: Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics

September 2014

851 pages

ISBN:9781450328944

DOI:10.1145/2649387

General Chairs:
Pierre Baldi
University of California, Irvine
,
Wei Wang
University of California, Los Angeles

Copyright © 2014 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGBio: ACM Special Interest Group on Bioinformatics

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 20 September 2014

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Conference

BCB '14

Sponsor:

SIGBio

BCB '14: ACM-BCB '14

September 20 - 23, 2014

California, Newport Beach

Acceptance Rates

Overall Acceptance Rate 254 of 885 submissions, 29%

Upcoming Conference

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
119
Total Downloads

Downloads (Last 12 months)1
Downloads (Last 6 weeks)0

Reflects downloads up to 26 Sep 2024

Other Metrics

View Author Metrics

Citations

Cited By

Rubio Delgado ERodríguez-Mazahua LPalet Guzmán JCervantes JCervantes JPeláez-Camarena SLópez-Chau A(2018)Analysis of Medical Opinions about the Nonrealization of Autopsies in a Mexican Hospital Using Association Rules and Bayesian NetworksScientific Programming10.1155/2018/43040172018Online publication date: 13-Feb-2018
https://dl.acm.org/doi/10.1155/2018/4304017
Rubio Delgado ERodríguez-Mazahua LPeláez-Camarena SAntonio Palet Guzmán JLópez-Chau A(2017)Association Analysis of Medical Opinions About the Non-realization of Autopsies in a Mexican HospitalNew Perspectives on Applied Industrial Tools and Techniques10.1007/978-3-319-56871-3_12(233-251)Online publication date: 17-Jun-2017
https://doi.org/10.1007/978-3-319-56871-3_12
Cheng CWang M(2015)Improving personalized clinical risk prediction based on causality-based association rulesProceedings of the 6th ACM Conference on Bioinformatics, Computational Biology and Health Informatics10.1145/2808719.2808759(386-392)Online publication date: 9-Sep-2015
https://dl.acm.org/doi/10.1145/2808719.2808759

View Options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents